TypeSafe's agent skill for Claude Code, Codex, and other coding agents.
typesafe-ai is TypeSafe's official agent skill, published by TypeSafe AI in typesafe-ai/skills ↗ under MIT. It is one instruction file that teaches your coding agent to design and write TypeSafe code: which judgments to ask Jev for, which primitive fits, and where to read the current docs.
It does not call Jev itself. Installing it adds no jev command, MCP server, or API client, and needs no API key. The code your agent writes with it calls the TypeSafe API, and that code needs your key.
The skills.sh installer asks which agents to install for and defaults to the current project; add -g for every project. Use one method per agent; TypeSafe warns that mixing them leaves duplicate copies. TypeSafe names Claude Code and Codex. Cursor and the other agents come from the installer's own list.
Which install to use
| If you | Use | Why |
|---|---|---|
| Only use Claude Code | The Claude Code plugin | TypeSafe's first-listed path. Installs once for your user, updates through Claude's plugin system, and is invoked as /typesafe:typesafe-ai. |
| Use Codex, Cursor, or several agents | npx skills add | Writes one portable copy that several agents read, and can link it into Claude Code too. There is no Codex plugin in the repository; Codex gets the portable skill. |
| Want the skill committed with a repo for your team | npx skills add (project scope, the default) | Files land inside the project, with a skills-lock.json recording the source and hash. |
| Can't run either installer | Manual copy | Copy the whole skills/typesafe-ai ↗ directory (currently SKILL.md and LICENSE) into your agent's skills directory. |
skills.sh also shows a URL form, npx skills add https://github.com/typesafe-ai/skills --skill typesafe-ai. It resolves to the same repository and skill as the short form TypeSafe documents.
Where it installs
The two installers have opposite defaults. The Claude plugin installs for your user account; skills.sh installs into the current project. We ran each in a throwaway directory to confirm where the files land.
| Method | Default scope | Files land in |
|---|---|---|
| Claude Code plugin | User (every project). --scope project or local to narrow it. | Claude Code's plugin cache under ~/.claude/plugins/ |
| skills.sh | Project | .agents/skills/typesafe-ai/ for Codex and Cursor. Claude Code gets .claude/skills/typesafe-ai: a symlink to that copy, or a plain copy if Claude Code is the only agent you pick. |
skills.sh with -g | User (every project) | The same layout under your home directory: ~/.agents/skills/typesafe-ai/ and ~/.claude/skills/typesafe-ai. |
Tested with skills 1.7.0 and Claude Code 2.1.258. -a accepts several agents (-a codex claude-code cursor); -y skips the prompts.
Claude Code vs. Codex
TypeSafe names both on its agent skill page ↗. The instructions are the same file either way: the plugin copy and the skills.sh copy of SKILL.md are byte-identical to the repository at v0.5.7. Packaging and invocation differ.
| Aspect | Claude Code | Codex |
|---|---|---|
| Install | Plugin typesafe@typesafe-ai (or skills.sh, choosing Claude Code) | npx skills add, choosing Codex |
| Package | Plugin typesafe 0.5.7 containing skill typesafe-ai | The bare skill directory |
| Explicit use | /typesafe:typesafe-ai for the plugin. A skills.sh copy is a plain skill, so it is /typesafe-ai. | Type $ to mention typesafe-ai, or pick it from /skills |
| Automatic use | Can load it when a task matches the skill's description | Can load it when a task matches the skill's description |
| Picking up updates | Restart or run /reload-plugins | Detected automatically; restart if not |
Naming it in the prompt (“use the TypeSafe skill”) is TypeSafe's suggestion for any agent. Invocation syntax comes from Claude Code's and OpenAI's skill docs; other agents have their own.
What your agent learns
The whole skill is SKILL.md ↗, about 150 lines. Claude Code's inventory for the plugin shows one skill and no agents, hooks, MCP servers, or LSP servers. It estimates about 170 tokens always in context (the description) and about 2.3k when the skill is invoked.
docs.typesafe.ai/llms.txt and the Markdown versions of the pages. If the agent can't reach the web, it should fall back to installed SDK types and say so rather than guess.instructions, the answers in criteria, a no-match outcome when nothing may fit. Question IDs are never sent to the model.What it is not
| It isn't | What that means |
|---|---|
A jev command or CLI | Nothing is added to your shell. The install is a Markdown file and a license. |
| An MCP server or agent tool | Your agent gains no tool that sends a judgment to Jev. Nothing new appears in /mcp. |
| An SDK | If the agent builds an integration, it adds TypeSafe's SDK or HTTP calls to your project like any other dependency. See the TypeScript SDK guide. |
| A local Jev or model weights | Jev still runs on TypeSafe's API or a provider such as OpenRouter. See open source & self-hosting. |
| A replacement for Claude or Codex | Jev can't power a coding agent. TypeSafe's coding-agents page ↗ says so directly: use your agent as usual to write code that uses Jev. |
Do you need an API key?
Not to install the skill, and not for the agent to design or write TypeSafe code with it. You need one when that code runs, or if you want the agent to try cheap test queries while it works. TypeSafe's own example exports the key as TYPESAFE_API_KEY and tells the agent to use it. Keys come from the TypeSafe console ↗; for providers, limits, and request setup, see API & access.
After installing
Ask for an outcome, not for the skill. TypeSafe's README uses this example:
Prompts that fit what the skill is built to do:
TYPESAFE_API_KEY, run a few test queries and propose changes from the best results.”Expect the agent to read TypeSafe's docs before it writes code. Review the questions and thresholds more closely than the plumbing. TypeSafe suggests keeping them in one file and notes that agents aren't great at writing questions. For worked designs, see the classification and model routing task pages.
Official skill vs. community tools
Searches for Jev with Claude Code or Codex also turn up independent projects that call Jev directly: MCP servers, command-line tools, and skills that shell out to a CLI. They're a different kind of thing, not an alternative install of TypeSafe's skill. We don't list or vet them here.
| Aspect | Official TypeSafe skill | Community executable tools |
|---|---|---|
| Publisher | TypeSafe AI (typesafe-ai GitHub org) | Independent developers |
| Installs | Instructions only | A binary, package, or server, sometimes with its own skill |
| Calls Jev during your session | No | Yes; that's their purpose |
| Credentials | None to install | A key or account set up on the tool |
| In TypeSafe's docs | Yes, with install instructions | No. The docs don't mention MCP at all. |
So if you installed the skill and expected a jev command or a Jev tool in your agent, nothing is broken. The skill changes what your agent knows, not what it can execute.
Updates & troubleshooting
/plugin, then Marketplaces → typesafe-ai → Enable auto-update. For a manual copy, replace the whole directory.Verified September 23, 2026 against the repository at tag v0.5.7 (plugin typesafe 0.5.7, marketplace typesafe-ai, skill typesafe-ai, MIT). The repository had 1,931 GitHub stars; skills.sh listed 64.2K installs and passing Gen Agent Trust Hub, Socket, and Snyk audits. Both installers were run in isolated directories; nothing was installed into a real agent configuration.